Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification

TL;DR

This paper introduces Reasoning-CV, a fine-tuning approach for large language models that improves claim verification by generating reasoning paths without decomposing claims, outperforming existing methods and black-box models.

Contribution

The paper proposes the Chain-of-Thought Verify paradigm and a fine-tuning method called Reasoning-CV, enhancing LLMs' claim verification without relying on claim decomposition.

Findings

Reasoning-CV outperforms existing Decompose-Then-Verify methods.

It surpasses powerful black-box LLMs like GPT-4o+CoT.

Uses only an 8B pre-trained LLM with superior results.

Abstract

Claim verification is essential in combating misinformation, and large language models (LLMs) have recently emerged in this area as powerful tools for assessing the veracity of claims using external knowledge. Existing LLM-based methods for claim verification typically adopt a Decompose-Then-Verify paradigm, which involves decomposing complex claims into several independent sub-claims and verifying each sub-claim separately. However, this paradigm often introduces errors during the claim decomposition process. To mitigate these errors, we propose to develop the Chain-of-Thought (CoT)-Verify paradigm, which leverages LLM reasoning methods to generate CoT-verification paths for the original complex claim without requiring decompositions into sub-claims and separate verification stages. The CoT-Verify paradigm allows us to propose a natural fine-tuning method called Reasoning-CV to enhance the verification capabilities in LLMs. Reasoning-CV includes a supervised fine-tuning (SFT) stage and a self-improvement direct preference optimization (DPO) stage. Utilizing only an 8B pre-trained LLM, Reasoning-CV demonstrates superior knowledge-assisted claim verification performances compared to existing Decompose-Then-Verify methods, as well as powerful black-box LLMs such as GPT-4o+CoT and o1-preview. Our code is available.